paper-with-me

홈 › Papers

Indirectly Parameterized Concrete Autoencoders

2024-03-01 · Alfred Nilsson, Klas Wijk, Sai Bharath Chandra Gutha, Erik Englesson, Alexandra Hotti, Carlo Saccardi, Oskar Kviman, Jens Lagergren, Ricardo Vinuesa, Hossein Azizpour

Feature selection is a crucial task in settings where data is high-dimensional or acquiring the full set of features is costly. Recent developments in neural network-based embedded feature selection show promising results across a wide range of applications. Concrete Autoencoders (CAEs), considered state-of-the-art in embedded feature selection, may struggle to achieve stable joint optimization, hurting their training time and generalization. In this work, we identify that this instability is correlated with the CAE learning duplicate selections. To remedy this, we propose a simple and effective improvement: Indirectly Parameterized CAEs (IP-CAEs). IP-CAEs learn an embedding and a mapping from it to the Gumbel-Softmax distributions' parameters. Despite being simple to implement, IP-CAE exhibits significant and consistent improvements over CAE in both generalization and training time across several datasets for reconstruction and classification. Unlike CAE, IP-CAE effectively leverages non-linear relationships and does not require retraining the jointly optimized decoder. Furthermore, our approach is, in principle, generalizable to Gumbel-Softmax distributions beyond feature selection.

📄 PDF Abstract BibTeX arXiv:2403.00563

Code (1)

alfred-n/ip-cae 공식 구현 pytorch

Tasks

Decoderfeature selection

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically
Feature Selection Feature selection, also known as variable selection, attribute selection or variable subset selection, is the process of selecting a subset of relevant features (variables,…

Similar Papers 제목 키워드 기반

Memorization in Overparameterized Autoencoders

2018-10-16 · ICML Workshop Deep_Phenomen 2019 6 · Adityanarayanan Radhakrishnan, Karren Yang, Mikhail Belkin, Caroline Uhler

The ability of deep neural networks to generalize well in the overparameterized regime has become a subject of significant research interest. We show that overparameterized autoencoders exhibit memorization, a form of in…

Inductive BiasMemorization

Associative Memory in Iterated Overparameterized Sigmoid Autoencoders

2020-06-30 · ICML 2020 1 · Yibo Jiang, Cengiz Pehlevan

Recent work showed that overparameterized autoencoders can be trained to implement associative memory via iterative maps, when the trained input-output Jacobian of the network has all of its eigenvalue norms strictly bel…

Learning Theoryregression

Overparameterized Neural Networks Implement Associative Memory

2019-09-26 · Adityanarayanan Radhakrishnan, Mikhail Belkin, Caroline Uhler

Identifying computational mechanisms for memorization and retrieval of data is a long-standing problem at the intersection of machine learning and neuroscience. Our main finding is that standard overparameterized deep ne…

MemorizationRetrieval

Fully Convolutional Graph Neural Networks using Bipartite Graph Convolutions

2020-01-01 · ICLR 2020 1 · Marcel Nassar, Xin Wang, Evren Tumer

Graph neural networks have been adopted in numerous applications ranging from learning relational representations to modeling data on irregular domains such as point clouds, social graphs, and molecular structures. Thoug…

Graph Neural Network

Concrete Autoencoders for Differentiable Feature Selection and Reconstruction

2019-01-27 · Abubakar Abid, Muhammad Fatih Balin, James Zou

We introduce the concrete autoencoder, an end-to-end differentiable method for global feature selection, which efficiently identifies a subset of the most informative features and simultaneously learns a neural network t…

Decoderfeature selectionGeneral ClassificationGeneral Classification Selection